Machine Learning Prediction of Collagen Fiber Orientation and Proteoglycan Content From Multiparametric Quantitative <scp>MRI</scp> in Articular Cartilage

Mirmojarabian, Sayed Amir; Kajabi, Abdul Wahed; Ketola, Juuso; Nykänen, Olli; Liimatainen, Timo; Nieminen, Miika T.; Nissi, Mikko J.; Casula, Victor

doi:10.1002/jmri.28353

Cited by 8 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy and feasibility of different machine learning models using quantitative MRI parameters in predicting cartilage matrix components were compared. 92 In this study, the ground truth was obtained from digital densitometry and polarized light microscopy. The Gaussian process regression (GPR) showed better performance than random forest, support vector regression, gradient boosting, and multilayer perceptron.…”

Section: Mr Fingerprinting and Multicontrast Methodsmentioning

confidence: 99%

“…Machine learning models have been investigated with quantitative MRI maps derived from MRF cartilage data in recent years. The accuracy and feasibility of different machine learning models using quantitative MRI parameters in predicting cartilage matrix components were compared 92 . In this study, the ground truth was obtained from digital densitometry and polarized light microscopy.…”

Section: Emerging Methods For Quantitative Mri For Cartilagementioning

confidence: 99%

See 1 more Smart Citation

Updates on Compositional MRI Mapping of the Cartilage: Emerging Techniques and Applications

Zibetti

Menon

Moura

et al. 2023

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Osteoarthritis (OA) is a widely occurring degenerative joint disease that is severely debilitating and causes significant socioeconomic burdens to society. Magnetic resonance imaging (MRI) is the preferred imaging modality for the morphological evaluation of cartilage due to its excellent soft tissue contrast and high spatial resolution. However, its utilization typically involves subjective qualitative assessment of cartilage. Compositional MRI, which refers to the quantitative characterization of cartilage using a variety of MRI methods, can provide important information regarding underlying compositional and ultrastructural changes that occur during early OA. Cartilage compositional MRI could serve as early imaging biomarkers for the objective evaluation of cartilage and help drive diagnostics, disease characterization, and response to novel therapies. This review will summarize current and ongoing state‐of‐the‐art cartilage compositional MRI techniques and highlight emerging methods for cartilage compositional MRI including MR fingerprinting, compressed sensing, multiexponential relaxometry, improved and robust radio‐frequency pulse sequences, and deep learning‐based acquisition, reconstruction, and segmentation. The review will also briefly discuss the current challenges and future directions for adopting these emerging cartilage compositional MRI techniques for use in clinical practice and translational OA research studies. Evidence Level 2 Technical Efficacy Stage 2.

show abstract

Section: Mr Fingerprinting and Multicontrast Methodsmentioning

confidence: 99%

Section: Emerging Methods For Quantitative Mri For Cartilagementioning

confidence: 99%

Updates on Compositional MRI Mapping of the Cartilage: Emerging Techniques and Applications

Zibetti

Menon

Moura

et al. 2023

Magnetic Resonance Imaging

View full text Add to dashboard Cite

show abstract

“…18 A very interesting application of ML techniques includes near infra-red spectroscopy for arthroscopic evaluation of articular cartilage [19][20][21] which might assess the damage to the cartilage in vivo more reliably than clinically accepted techniques, and without the need for a similarly ANN-supplemented MRI diagnostics. 22…”

Section: Musculoskeletal Applicationsmentioning

confidence: 99%

“…Multiple studies have firmly estimated the usefulness of this technique to estimate a horse's speed, 14,15 gait 16,17 and ground reaction forces 18 . A very interesting application of ML techniques includes near infra‐red spectroscopy for arthroscopic evaluation of articular cartilage 19–21 which might assess the damage to the cartilage in vivo more reliably than clinically accepted techniques, and without the need for a similarly ANN‐supplemented MRI diagnostics 22 …”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence: Is it wizardry, witchcraft, or a helping hand for an equine veterinarian?

Alexeenko

Jeevaratnam

2023

Equine Veterinary Journal

View full text Add to dashboard Cite

It is extremely likely that in this decade artificial intelligence (AI) will become a tool that will affect biosciences and medicine in no lesser degree than genetics did in the 1980s. The need for personalised care for patients, the drive for evidence-based medicine, as well as the need for reduction of human error in human and veterinary medicine are strongly motivating the acceptance of AI techniques.They are expected to eliminate uncertainties of human reasoning and abolish the limits of knowledge which could be acquired by a single medical expert or even a panel of such experts. However, for most healthcare professionals AI continues to be a poorly understood technology, which consequently is adopted slowly or even outright feared. The equine veterinary sector is no exception. Given that veterinary education does not typically include much exposure to mathematics or computer science, and the importance of equine theriogenology, it is not surprising that only about one in 20 papers found by the keywords 'AI' and 'equine' now refers to artificial intelligence and not to other techniques used in veterinary medicine.Still, the number of papers using AI in equine veterinary medicine is exponentially growing, and the 2019-2022 plateau of approximately 20 papers per year will surely be exceeded this year. In this context, it might be useful to revisit the main concepts in AI and review its application by equine veterinarians.

show abstract

“…In this issue of JMRI, Mirmojarabian et al 8 report on the feasibility of five machine-learning models that were used in combination with quantitative MRI parameters to estimate cartilage composition and structure. In this well-designed study, a remarkable number of qMRI parameters ( 14) and five machine-learning algorithms, including gradient boosting, support vector regression, random forest, Gaussian process regression, and multi-layer perceptron, were used.…”

mentioning

confidence: 99%

Editorial for “Machine Learning Prediction of Collagen Fiber Orientation and Proteoglycan Content From Multiparametric Quantitative MRI in Articular Cartilage”

Juráš

2022

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Machine Learning Prediction of Collagen Fiber Orientation and Proteoglycan Content From Multiparametric Quantitative MRI in Articular Cartilage

Abstract: This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Cited by 8 publications

References 34 publications

Updates on Compositional MRI Mapping of the Cartilage: Emerging Techniques and Applications

Updates on Compositional MRI Mapping of the Cartilage: Emerging Techniques and Applications

Artificial intelligence: Is it wizardry, witchcraft, or a helping hand for an equine veterinarian?

Editorial for “Machine Learning Prediction of Collagen Fiber Orientation and Proteoglycan Content From Multiparametric Quantitative MRI in Articular Cartilage”

Contact Info

Product

Resources

About